Search form

 

Search form


  • Bokmål
  • English

Sitemap

Image Analysis and Machine Learning

Image Analysis and Machine Learning

We have extensive knowledge and more than 30 years experience in the fields of image analysis and machine learning, and practical experience from a wide range of applications.

Object extraction, characterization and recognition from images are central for many of these applications. Other central themes are analysis of sequences of data and pattern recognition applied to unstructured text. Pattern recognition is not restricted to images, and we also have experience with other types of data such as acoustic signals, audio and text. In particular, pattern recognition in unstructured text has become popular with the steadily increasing amounts of text based information available online.

Solutions to the problems are often found through approaches that combine prior information and context with the observed data (images, video, text etc) in a simple but yet efficient way.

Read more about Deep Learning for applications.

Selected projects

COGMAR - Ubiquitous cognitive computer vision for marine services
Deep Learning for Applications
The image analysis and machine learning group at NR and the machine learning group at UiT work together to better understand the needs and to develop state-of-the-art specialized deep learning solutions suitable for solving specific problems for various industry-, medical and environmental applications, and within analysis of remote sensing images.
Efficient search for biomedical information
Document collections resulting from literature searches are often so large that some organization of the returned information is necessary. In this project solutions have been developed that enable clustering along with textual labels and summaries of search results from biomedical literature databases. In addition, a novel concept of multi-focus cluster labeling is introduced to provide labels from multiple viewpoints.
Extracting information from historical Norwegian census forms
This is part of a larger initiative to establish a historical population register for Norway. Establishing such a database requires transcription of a large amount of historical records. Where possible it is desirable to be able to automate parts of this transcription process, and NR is working with image based methods to automate extraction of information from historical Norwegian census forms.
HyperBio
LasTrak
Automatic mapping of forest roads
Removal of clutter from historical scanned documents
This project, led by Lumex A/S, aims to improve optical character recognition in noisy historical documents. The goal is to develop solutions that will be able to detect, locate and characterize clutter and then apply adapted OCR to regions containing clutter.
Ultralydinspeksjon av komposittmaterialer
Ultralyd brukes til ikke-destruktiv inspeksjon av ulike materialer, der komposittmaterialer byr på spesielle utfordringer. DolphiTech har nå utviklet en ny type verktøy for ultralydinspeksjon for blant annet komposittmaterialer, der NR skal se på signal/bildebehandling for best mulig visualisering av observasjonene.

Contact information

Department

Related pages

Postal address:
Norsk Regnesentral/
Norwegian Computing Center
P.O. Box 114 Blindern
NO-0314 Oslo
Norway 		Visit address:
Norsk Regnesentral
Gaustadalleen 23a
Kristen Nygaards hus
NO-0373 Oslo.
 Phone:
(+47) 22 85 25 00
Address How to get to NR
Social media Share on social media
Privacy policy Privacy policy
Postal address: Norsk Regnesentral/Norwegian Computing Center, P.O. Box 114 Blindern, NO-0314 Oslo, Norway
Visit address: Norsk Regnesentral, Gaustadalleen 23a, Kristen Nygaards hus, NO-0373 Oslo.
Phone: (+47) 22 85 25 00
AddressHow to get to NR